@magyk/vincent 0.1.14 → 0.1.15

package/CHANGELOG.md

@@ -6,6 +6,27 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ---
 
+## [0.1.15] — 2026-05-13
+
+### Added
+- **`/new` command** — start a fresh session in-place without restarting the TUI.
+  Clears the chat, creates a new work directory, and re-shows the welcome message.
+  Blocked while an agent operation is in progress; any active proposal is dismissed
+  cleanly before the reset.
+- **Conversation history on resume** — when picking up a previous session, the last
+  few exchanges (up to ~5 user-assistant pairs) are replayed into the chat so you
+  can see where things left off. Thinking traces, tool calls, and internal context
+  messages are filtered out; product images are shown inline if the terminal supports it.
+
+### Changed
+- **Longer animation prompts for Veo** — when a Veo model is selected, the
+  animation prompt generator now targets up to 200 words (previously capped at
+  ~100 words for all models). Hailuo remains at 100 words. The word budget is
+  defined per-model in the capabilities registry, so future models can set their
+  own limit without any branching in tool code.
+
+---
+
 ## [0.1.14] — 2026-05-13
 
 ### Added

package/README.md

@@ -8,28 +8,18 @@ No video editing skills required.
 
 Built on Google Gemini (LLM + image generation) and Veo3 (video generation).
 
-## Getting Started
+## Requirements
 
-### 1. Install Node.js 25
+Node.js ≥ 25. Install via [nvm](https://github.com/nvm-sh/nvm): `nvm install 25 && nvm use 25`.
 
-Vincent requires Node.js 25 or later. The easiest way is [nvm](https://github.com/nvm-sh/nvm):
-
-```bash
-curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash
-source ~/.nvm/nvm.sh
-nvm install 25
-nvm use 25
-node --version   # should print v25.x.x
-```
-
-### 2. Install Vincent
+## Install
 
 ```bash
 npm install -g @magyk/vincent
 vincent --version
 ```
 
-### 3. Get a Google API key
+## Get a Gemini API key
 
 [Google AI Studio](https://aistudio.google.com) is the fastest way to get a key — one key covers the LLM, image generation, and Veo video generation.
 
@@ -38,63 +28,33 @@ vincent --version
 3. Click **Create API key**. You can create it in a new or existing Google Cloud project.
 4. Copy the key and keep it somewhere safe — you'll paste it into Vincent on first run.
 
-> **Billing note:** AI Studio uses a tiered billing system (Prepay and Postpay). New accounts start on a free tier with generous rate limits. For high-volume or production use you'll need to link a billing account.
+> **Billing note:** AI Studio uses a tiered billing system. New accounts start on a free tier with generous rate limits. For high-volume or production use you'll need to link a billing account.
 
-### 4. Make your first video
+## Usage
 
 ```bash
-vincent path/to/product-image.jpg
-```
-
-On first run, Vincent will ask you to paste your Gemini API key — it saves it automatically so you only need to do this once. Then describe what you want; it will propose a concept, generate scene images, animate them with Veo3, and assemble the final video in your working directory.
-
----
-
-## Install
-
+vincent                          # start a new session
+vincent product.jpg              # start with an image already loaded
+vincent --image product.jpg      # same, explicit flag (useful in scripts)
 ```
-npm install -g @magyk/vincent
-```
-
-Requires Node.js ≥ 25.
 
-## Quickstart
-
-```
-export GEMINI_API_KEY=your_key_here
-vincent path/to/product-image.jpg
-```
+**First run:** Vincent will prompt you to paste your Gemini API key — it's saved automatically and you won't be asked again. The TUI will show you how to provide an image and what commands are available.
 
-Vincent opens an interactive session. Describe what you want; it will propose a concept,
-generate scene images, animate them, and produce a final video in your working directory.
-
-## Configuration
-
-On first run, Vincent creates a settings file at:
-- **Linux:** `~/.local/share/magyk/settings.json`
-- **macOS:** `~/Library/Application Support/magyk/settings.json`
-
-You can also use `/settings` inside the TUI to configure API keys and model preferences,
-or set `GEMINI_API_KEY` in your environment (takes priority over the settings file).
+API keys are stored in `~/.local/share/magyk/settings.json` (Linux) or `~/Library/Application Support/magyk/settings.json` (macOS). You can also use `/settings` inside the TUI to manage them, or set `GEMINI_API_KEY` in your environment (takes priority over the saved key).
 
 ## Options
 
 ```
-vincent [image-url-or-path] [options]
+vincent [image] [options]
 
-  --image <url|path>     Product image (also accepted as a positional arg)
+  --image <url|path>     Product image URL or local path (equivalent to positional arg)
   --video-model <id>     veo3 or veo3-lite (default: veo3-lite)
   --storage <path>       Override artifact output directory
   --self-test            Run built-in diagnostics and exit
+  --version, -v          Print version and exit
   -h, --help             Show help
 ```
 
-## Output
-
-Each session creates a directory under `~/.local/share/magyk/genartifacts/` (Linux)
-or `~/Library/Application Support/magyk/genartifacts/` (macOS) containing the original
-image, generated scene images, and the final assembled video.
-
 ## License
 
 See [LICENSE](https://www.npmjs.com/package/@magyk/vincent?activeTab=code) for terms.